US20100010957A1 - Methods for the Construction and Maintenance of a Computerized Knowledge Representation System - Google Patents

Methods for the Construction and Maintenance of a Computerized Knowledge Representation System Download PDF

Info

Publication number
US20100010957A1
US20100010957A1 US12/499,761 US49976109A US2010010957A1 US 20100010957 A1 US20100010957 A1 US 20100010957A1 US 49976109 A US49976109 A US 49976109A US 2010010957 A1 US2010010957 A1 US 2010010957A1
Authority
US
United States
Prior art keywords
fact
krs
templates
information
knowledge
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
US12/499,761
Other versions
US8392353B2 (en
Inventor
Raymond J. Cho
Richard O. Chen
Ramon M. Felciano
Daniel R. Richards
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ingenuity Systems Inc
Original Assignee
Ingenuity Systems Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US09/733,495 external-priority patent/US6772160B2/en
Priority claimed from US10/038,197 external-priority patent/US6741986B2/en
Application filed by Ingenuity Systems Inc filed Critical Ingenuity Systems Inc
Priority to US12/499,761 priority Critical patent/US8392353B2/en
Assigned to INGENUITY SYSTEMS, INC. reassignment INGENUITY SYSTEMS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: CHEN, RICHARD O., CHO, RAYMOND J., FELCIANO, RAMON M., RICHARDS, DANIEL R.
Publication of US20100010957A1 publication Critical patent/US20100010957A1/en
Assigned to INGENUITY SYSTEMS, INC. reassignment INGENUITY SYSTEMS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: CHEN, RICHARD O., CHO, RAYMOND J., FELCIANO, RAMON M., RICHARDS, DANIEL R.
Priority to US13/745,605 priority patent/US9514408B2/en
Application granted granted Critical
Publication of US8392353B2 publication Critical patent/US8392353B2/en
Adjusted expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367Ontology
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/02Knowledge representation; Symbolic representation
    • G06N5/022Knowledge engineering; Knowledge acquisition
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99941Database schema or data structure
    • Y10S707/99944Object-oriented database structure
    • Y10S707/99945Object-oriented database structure processing
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99941Database schema or data structure
    • Y10S707/99948Application of database or data structure, e.g. distributed, multimedia, or image

Definitions

  • genomics The explosion of published information in the fields of biology, biochemistry, genetics and related fields (collectively referred to herein as “genomics”) presents research scientists with the enormous challenge of searching and analyzing a massive amount of published information to find the particular information of interest.
  • the majority of new genomics information is produced and stored in text form.
  • Information stored in text form is unstructured and, other than key word searches of various types, relatively inaccessible to standard computer search techniques.
  • Text storage was never designed for and has not proven adequate to the task of describing and clarifying the complex, interrelated biochemical pathways involved in biological systems.
  • Examples of high-level computational tasks that cannot be performed on text-based databases include: a) computational identification of clusters of diverse functionally interrelated genes that occur in genomic data sets; b) systematic, principled prediction of gene function using computation over links between uncharacterized genes and other genes in the genome, using all functional relationships available in the literature rather than just the available experimental genomic data sets; c) novel biological inferences in the knowledge base, based on computation over large bodies of existing, explicitly entered content; and d) flexible computation of the genes that constitute biological pathways, based on criteria such as upstream versus downstream genes, transcriptional versus phosphorylation targets, membrane-bound versus nuclear genes, etc.
  • KRS knowledge representation system
  • KB knowledge acquisition
  • KA knowledge acquisition
  • KA is recognized as a slow, difficult and expensive process.
  • KA is a major and perhaps the major bottleneck in building functional and useful KBs.
  • a consequence of the difficulties associated with KA is that most KBs are small and concentrate on a very limited domain of interest.
  • KE knowledge representation expert or knowledge engineer
  • the KE transcribes, structures and embeds this information into the KB.
  • KEs must have an understanding of the underlying formal machine representation of the KRS in order to extract the information from the text source and then insert the information into the KRS in a consistent, accurate and appropriate manner.
  • the KE works closely with scientific experts to classify and categorize the information properly.
  • the need for two highly trained individuals to work together to structure and enter the information makes this approach to populating a KRS extremely time consuming and expensive.
  • Various embodiments provide a web-accessible, KRS-based KA system, enabling all interested biological scientists (“scientists”), with no specific training in knowledge modeling or computer science, to extract information without direct interaction with KEs.
  • scientists interested biological scientists
  • KA knowledge modeling or computer science
  • KA To enable KA according to some embodiments involves factors such as a) the acquisition and structuring of the captured knowledge in a form strictly consistent with the KRS; and b) a KA process usable by a widely distributed group of scientists.
  • KA fact templates are the entry point for information taken from various sources and comprise a logical series of text boxes with pull-down menu selections.
  • the content and configuration of these fact templates is driven by and directly linked to the content and fact model structure of the overall KRS.
  • the templates are constructed to capture all fact types, relationships, objects and processes, as well as all associated details of these concepts contained in the KRS.
  • the training tools for teaching the scientists how to complete the templates are available through a web site. After studying the web-accessible training modules, a scientist takes a web-accessible certification test, the successful completion of which is generally necessary for the scientist to submit completed templates for entry into the KRS. The scientist who submits completed templates is designated as a content scientist.
  • quality control scientists typically have qualified for the quality control role by either additional training or exemplary performance at the entry-level knowledge entry position. For content scientists who have reached a certain skill level, every template need not be reviewed by a quality control scientist.
  • the templates, trained scientists, and quality control personnel permit the rapid population of the KRS with verified findings.
  • the resulting KB can be maintained and expanded at a rate much greater than that allowed by known methods for populating other KRSs.
  • FIG. 1 illustrates an example ontology
  • FIGS. 2 a and 2 b show, respectively, an example of a fact as it appears in the literature and a fact after it has been abstracted;
  • FIG. 3 is a flow chart of one type of fact captured by the templates
  • FIG. 4 illustrates a first selection menu for entry of the fact type shown in FIG. 3 ;
  • FIG. 5 illustrates a second set of selection menus for the fact type of FIG. 3 ;
  • FIG. 6 illustrates yet another menu for entry of the fact type of FIG. 3 ;
  • FIG. 7 illustrates how information in the template maps to the KRS structure.
  • FIG. 8 illustrates a schematic of a computer system that can be used to construct, maintain, query and populate a knowledge representation system.
  • a first embodiment comprises a method for deconstructing experimental findings originally occurring in narrative text or symbolic (e.g., graphical or tabular) documents, structuring and codifying these findings by means of templates and then storing the information contained in the completed templates in a KRS to create a KB.
  • the data architecture used in this embodiment is herein referred to as an ontology.
  • An ontology is a hierarchical representation of the taxonomy and formal concepts and relationships relevant to the domain of interest stored in a knowledge representation system (“KRS”).
  • KRS knowledge representation system
  • an ontology is a specific form of a KRS.
  • the KRS may be a frame-based, rule-based or other type of database architecture, the choice of which may depend on a variety of factors, such as storage needs.
  • a frame-based KRS is used. Therefore, for purposes of describing the KRS of one embodiment, reference will be made to a frame-based KRS.
  • other known types of data architecture may alternatively be used in connection with some embodiments, as will become apparent.
  • the domain of interest is genomic information, which comprises at a minimum information relating to genes, their DNA sequences, the proteins which result when the genes are expressed, the biological effects of the expressed proteins and other, related information.
  • genomic information comprises at a minimum information relating to genes, their DNA sequences, the proteins which result when the genes are expressed, the biological effects of the expressed proteins and other, related information.
  • the ontology must be formally defined and organized.
  • the primary organizational component of the ontology in a frame-based KRS is the class.
  • Classes are descriptions of particular categories of objects.
  • Properties are attributes that describe the class itself or relate one class to another.
  • An instance is an actual example of a class, and the relationship between two different instances in the ontology is defined by slots. Slots can be thought of as the verbs that relate and link two classes.
  • frame-based KRSs support basic inference capabilities such as classification and declarations of axioms. Axioms impose semantic constraints on the ontology that help to maintain the consistency and integrity of the data.
  • Frame-based KRSs also provide basic query capabilities for retrieving stored data. Populating the frame-based KRS with real world examples of experimental information transforms the system into a KB.
  • FIG. 1 is a diagram of a portion of an ontology, illustrating the concepts of classes, properties and instances, as well as examples of experimental information that reside in the KB described herein.
  • ontology 10 has three sub-parts 15 , 20 and 25 .
  • Sub-part 15 belongs to the class of interaction data and has three properties: effector, affected, and interaction type.
  • Below sub-part 15 are sub-parts 20 and 25 , respectively having the classes of phosphorylation assay and cell assay.
  • Sub-parts 20 and 25 are both sub-classes of the class interaction data. Each sub-class inherits all the properties of its parent class. In the case of sub-class phosphorylation assay 20 , an additional property of time-required is added.
  • the additional property added is reagents-used.
  • Each sub-class shown in sub-parts 20 and 25 is shown linked to one instance of the respective subclass.
  • Instance 30 is an instance of subclass 20 and instance 35 is an instance of subclass 25 .
  • the particular properties for instances 30 and 35 are filled in with actual values. Some of these values are examples of biological entities categorized and captured in other parts of the ontology.
  • the effector PKC in instance 30 is an instance of a kinase, while the affected CREB is a transcription factor. Both the effector and affected are within the class of molecules and the subclass of proteins, as shown in molecule sub-ontology 40 .
  • the effector is IL-4, which is a member of the class cytokines, shown in sub-ontology 40
  • the affected, B-Lymphocyte is a lymphocytes in immune cells sub-ontology 45 .
  • the fact that the same object can belong to several different classes explains why searching across the KB can generate results that are not readily apparent from the individual items entered into it.
  • the illustrated ontology represents only a very small portion of the ontology that will be constructed using the methods of this first embodiment described herein.
  • the KB of various embodiments requires translating information from source text (e.g., information expressed in a natural language, such as English) and/or symbolic data (e.g., graphical or tabular data) into a computational information language.
  • source text e.g., information expressed in a natural language, such as English
  • symbolic data e.g., graphical or tabular data
  • the information is biological information, although it will be apparent to one skilled in the art that other types of information could be stored in a KB.
  • the process of translating information is called structuring knowledge, as it places knowledge, in this case biological findings, into the structure and architecture of the KRS.
  • the method for structuring the knowledge is based on formalized models of experimental design and biological concepts. These models provide the framework for capturing a considerable portion of the loosely articulated findings typically found in academic literature. The specific level of experimental results that is of greatest value to industrial and academic scientists can be particularly targeted for capture. So, for example, in the field of genomics, knowledge that focuses on the effects that both perturbation to genes, gene products (RNA and proteins) and small molecules and various physical stimuli have upon biological systems is singled out. These perturbations and stimuli form the backbone of the KRS and provide the necessary framework for developing a more sophisticated representation of complex biological information.
  • Examples of the types of facts and biological relationships that can be translated into the KRS are: a) an increase in the amount of Fadd protein increases apoptosis; b) a decrease in Raf levels increases activation of Rip2; and c) the allele delta32 of CCR5, compared to the wild-type allele, decreases HIV transmission.
  • biological systems are defined in terms of processes and objects.
  • Discrete objects are physical things such as specific genes, proteins, cells and organisms. Processes are actions that act on those objects. Examples of processes include phosphorylation, which acts on discrete objects such as proteins, and apoptosis, which acts on cells. Perturbation of an object can have an effect on a process or on an object.
  • the information in the KB may be represented by a variety of fact types. In one embodiment, two distinct fact types of interest are: a) case-control facts; and b) observational facts.
  • a case-control fact describes those experimental results wherein a discrete object, such as a protein or a drug, or a specific physical stimulus, such as hypoxia, is added to a biological or biochemical system and the corresponding changes in the system are monitored and measured.
  • a case-control fact is, “expression of hRas from a viral vector increases the phosphorylation of MAPK in 293 cells.”
  • An observational fact reports an observation, not the alteration of a biological system by an effector.
  • An example of an observational fact is, “examination of cells using laser scanning confocal microscopy revealed that Bcl-2 localizes to the mitochondria of 293 cells.”
  • the KRS In order to construct the KRS, each of these building blocks-objects, processes and experimental fact types, has been rigorously defined and characterized. Additionally, the KRS is able to store the appropriate details associated with all the processes (including process properties, modifiers and mediators), objects (including mutations, allele names and physical location). Capturing these details and creating varying levels of abstraction are necessary if the populated KB is to reflect the dynamic, complex and interconnected nature of biological findings.
  • FIGS. 2 a and 2 b illustrate how fact model types can be used to deconstruct the semantics of text-based information into its proper constituent components and then model and structure those components.
  • information to be extracted may exist in a text-based format, graphical form, or a combination of text and graphics.
  • information is presented in both text and graphical form in a research article in the peer-reviewed literature.
  • a text paragraph 60 represents an experimental finding indicating that expression of a mutant form of the human protein Trf2 leads to increased frequency of chromosome end fusions, anaphase bridges and lagging chromosomes.
  • FIG. 2 b the fact of FIG. 2 a has been deconstructed.
  • Metadata 75 presents information related to the experiment from which the fact was derived.
  • the metadata includes the type of experiment and the method used to visualize the experiment's results.
  • fact templates In order to maintain consistency in the deconstruction of the text-based (or symbolic) information and to insure that knowledge is acquired and structured in a manner strictly consistent with the KRS, fact templates have been designed and implemented. These templates are the tools used by scientists to take information extracted from source text, graphics, or a combination thereof, and to format that information so that it can be entered in the KRS.
  • the templates may be accessible over the web and comprise a logical series of text boxes, with pull-down menus assigned to each text box.
  • the content and configuration of these fact templates is driven by the content and fact model structure of the KRS.
  • the templates are constructed to capture all fact types, relationships, objects and processes, as well as all associated details of these concepts, contained in the KRS. A scientist entering data into the templates cannot enter terms not contained in the KRS unless these new terms are marked as new and reviewed in the manner described below.
  • case control fact 101 comprises an effector 103 which causes a change of direction 105 to a property 107 of an object 109 .
  • a specific example of a case control fact “. . . in 293 cells, transient overexpression of mouse (mus) Fas induced apoptosis in a dose-dependent manner,” has an effector (the protein Fas) which causes a change (induction) of a property (apoptosis) in an object (293 cells).
  • Fas the protein Fas
  • FIG. 4 illustrates how the appropriate case control template would initially appear to the scientist.
  • the image shown in FIG. 4 is displayed.
  • the template displays a menu box 111 for protein and cellular process
  • the scientist knows that the correct template has been chosen for this particular example, as a protein effector Fas has been shown to cause a change in a cellular process, here apoptosis.
  • Several different but similar templates are used for other modifications of case control facts, observational fact, or other fact types.
  • the initial basic information that is entered into the fact type template automatically dictates the next frame that will be shown to the scientist to capture all details of a given fact.
  • the scientist is prompted to provide further information on the protein involved.
  • the scientist is first provided with a text box 112 that allows entry of a few letters of the effector name (in the example given, the scientist could type an F, fas, mus, etc.) and possible exact matches will be presented in a drop down list.
  • the appropriate selection in this example is Fas mouse (mus) protein.
  • the scientist is presented with text boxes and associated pull-down menus, which offer constrained choices for entering the main components of the fact-properties, objects and their associated details, as defined by the KRS.
  • pull-down menus the user could be presented with a type-in field. In this embodiment, the user input would be checked against a predefined list of information choices acceptable to the fact type. In still another embodiment, a user could be presented with icons for selecting valid field values.
  • the next step in this example is to enter any details associated with the Fas mouse protein. Access to additional menus for specified details of an object is enabled by clicking on a “details” button.
  • various embodiments ensure that information is structured in a way that is consistent with the hierarchical organization and controlled vocabulary of the KRS.
  • FIG. 7 is an illustration of how a completed fact template maps graphically to the data architecture of the KRS.
  • a new item slot is made available within the template for the user to insert the new term.
  • the new item slot appears when the term is not presented in the templates or if the term, after being typed into a text box, is not recognized by the KRS. Entries made into the new item slot are automatically flagged and later evaluated by KEs for incorporation within the KRS.
  • the use of the fact templates allows various embodiments to acquire knowledge for the KRS that is structured completely in accordance with instances already within the KRS, to express distinct types of experimental propositions in distinct fact structures, to ascribe standardized meanings for each component of the sentences of text-based information to be incorporated with the KRS, to utilize absolutely consistent terminology and to utilize concepts at distinct but interrelated levels of abstraction.
  • the KB can be expanded very rapidly, with only occasional intervention by the KEs when new concepts and terms are found.
  • some embodiments include code on a computer readable medium.
  • the computer readable medium can be one or a combination of memory 803 , processor 801 , hard disk, CD 811 , DVD 812 , floppy, and/or carrier wave traveling a wired and/or wireless network 805 , etc.

Abstract

Methods for constructing and maintaining knowledge representation systems are disclosed herein. The knowledge representation system is initially organized and populated using knowledge engineers. After the initial organization, scientific domain experts digest and structure source texts for direct entry into the knowledge representation system using templates created by the knowledge engineers. These templates constrain both the form and content of the digested information, allowing it to be entered directly into the knowledge representation system. Although knowledge engineers are available to evaluate and dispose of those instances when the digested information cannot be entered in the form required by the templates, their role is much reduced from conventional knowledge representation system construction methods. The methods disclosed herein permit the construction and maintenance of a much larger knowledge representation system than could be constructed and maintained using known methods.

Description

    REFERENCE TO RELATED APPLICATIONS
  • This application is a divisional application and claims the benefit of priority under 35 USC § 121 of U.S. patent application Ser. No. 10/770,864, filed on Feb. 2, 2004, which is a continuation-in-part of and claims the benefit of priority under 35 USC § 120 of U.S. patent application Ser. No. 09/733,495, filed on Dec. 8, 2000, now issued as U.S. Pat. No. 6,772,160 on Aug. 3, 2004 and U.S. patent application Ser. No. 10/038,197, filed on Nov. 9, 2001, now issued as U.S. Pat. No. 6,741,986 on May 25, 2004; and further claims the benefit of priority under 35 USC § 119(e) to U.S. Provisional Applications Ser. Nos. 60/210,898, filed Jun. 8, 2000; 60/229,582, filed Aug. 31, 2000; 60/229,581, filed Aug. 31, 2000; 60/229,424, filed Aug. 31, 2000; and 60/229,392, filed Aug. 31, 2000, which are incorporated herein by reference in their entirety.
  • BACKGROUND
  • The explosion of published information in the fields of biology, biochemistry, genetics and related fields (collectively referred to herein as “genomics”) presents research scientists with the enormous challenge of searching and analyzing a massive amount of published information to find the particular information of interest. The majority of new genomics information is produced and stored in text form. Information stored in text form is unstructured and, other than key word searches of various types, relatively inaccessible to standard computer search techniques.
  • The process of culling and reviewing relevant information from the published literature is consequently a laborious and time-consuming one. Even the most basic queries about the function of a particular gene using even sophisticated key word searches often result in generating too many articles to be reviewed carefully in a reasonable amount of time, missing critical articles with important findings expressed in a non-standard manner and form or both.
  • Text storage was never designed for and has not proven adequate to the task of describing and clarifying the complex, interrelated biochemical pathways involved in biological systems. Examples of high-level computational tasks that cannot be performed on text-based databases include: a) computational identification of clusters of diverse functionally interrelated genes that occur in genomic data sets; b) systematic, principled prediction of gene function using computation over links between uncharacterized genes and other genes in the genome, using all functional relationships available in the literature rather than just the available experimental genomic data sets; c) novel biological inferences in the knowledge base, based on computation over large bodies of existing, explicitly entered content; and d) flexible computation of the genes that constitute biological pathways, based on criteria such as upstream versus downstream genes, transcriptional versus phosphorylation targets, membrane-bound versus nuclear genes, etc.
  • By limiting a researcher's ability to ask these types of questions when searching for information, the current text-based model of information storage is a serious obstacle to research in genomics. The ever-increasing volume of functional genetic data resulting from the biotechnology revolution further demonstrates how both the academic and industrial communities require a more readily computable means for archiving and mining the genomics information.
  • The desirability of placing the published genomics information into a structured format and thus allowing easier and more useful searches is known, for example by storing information extracted from text in a frame-based knowledge representation system. Although examples of frame-based knowledge representation systems are known in several fields, the difficulties in populating such a system with specific genomics information, leading to the creation of a true genomics knowledge base are substantial.
  • The process to populate a frame-based knowledge representation system (herein “KRS”) with information, leading to the creation of what is called a “knowledge base,” (“KB”) is known as knowledge acquisition (KA). KA is recognized as a slow, difficult and expensive process. KA is a major and perhaps the major bottleneck in building functional and useful KBs. A consequence of the difficulties associated with KA is that most KBs are small and concentrate on a very limited domain of interest.
  • Known methods of performing the KA function require a knowledge representation expert or knowledge engineer (KE) with computer science training to work with the appropriate domain experts to manually capture and then organize the extracted information into the KRS. The KE transcribes, structures and embeds this information into the KB. KEs must have an understanding of the underlying formal machine representation of the KRS in order to extract the information from the text source and then insert the information into the KRS in a consistent, accurate and appropriate manner. Often the KE works closely with scientific experts to classify and categorize the information properly. The need for two highly trained individuals to work together to structure and enter the information makes this approach to populating a KRS extremely time consuming and expensive. These problems also greatly restrict the extent to which this process can be used as the amount of information to be captured increases.
  • As millions of findings must be captured and structured to create a KB of the size and scope necessary for useful genomics research, a method for efficiently and economically populating a genomics KRS with structured, codified information to create a usable KB is needed.
  • SUMMARY
  • Various embodiments provide a web-accessible, KRS-based KA system, enabling all interested biological scientists (“scientists”), with no specific training in knowledge modeling or computer science, to extract information without direct interaction with KEs. By enabling a distributed group of scientists to populate the KRS, without requiring these scientists to understand the details of the KRS's structure or implementation, potentially hundreds of scientists can be employed on a consultant basis for the KA task. This permits the population of the KRS at a rate that is tens to hundreds of times faster than the known use of in-house KEs to populate a KRS, at a fraction of the cost. Various embodiments allow for the disassociation of the knowledge engineering and knowledge acquisition processes.
  • To enable KA according to some embodiments involves factors such as a) the acquisition and structuring of the captured knowledge in a form strictly consistent with the KRS; and b) a KA process usable by a widely distributed group of scientists.
  • The first requirement can be met by the use of KA fact templates. These templates are the entry point for information taken from various sources and comprise a logical series of text boxes with pull-down menu selections. The content and configuration of these fact templates is driven by and directly linked to the content and fact model structure of the overall KRS. The templates are constructed to capture all fact types, relationships, objects and processes, as well as all associated details of these concepts contained in the KRS.
  • As new concepts and terms not originally represented in the KRS will certainly be found in the future, provisions can be made to allow entry into the template of new information types. The entry of such new information causes the template to be flagged for examination by one of a small group of KEs. Upon examination, and as appropriate, the KRS will be modified and the new finding or term entered into it. The templates can then be modified or additions made to their pull-down menus to accommodate the changes.
  • The training tools for teaching the scientists how to complete the templates are available through a web site. After studying the web-accessible training modules, a scientist takes a web-accessible certification test, the successful completion of which is generally necessary for the scientist to submit completed templates for entry into the KRS. The scientist who submits completed templates is designated as a content scientist.
  • As part of an on-going and necessary quality control process, some or all completed templates are reviewed by quality control scientists. These quality control scientists typically have qualified for the quality control role by either additional training or exemplary performance at the entry-level knowledge entry position. For content scientists who have reached a certain skill level, every template need not be reviewed by a quality control scientist.
  • The templates, trained scientists, and quality control personnel permit the rapid population of the KRS with verified findings. The resulting KB can be maintained and expanded at a rate much greater than that allowed by known methods for populating other KRSs.
  • Some embodiments are described in detail, with reference to the figures listed and described below.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIG. 1 illustrates an example ontology;
  • FIGS. 2 a and 2 b show, respectively, an example of a fact as it appears in the literature and a fact after it has been abstracted;
  • FIG. 3 is a flow chart of one type of fact captured by the templates;
  • FIG. 4 illustrates a first selection menu for entry of the fact type shown in FIG. 3;
  • FIG. 5 illustrates a second set of selection menus for the fact type of FIG. 3;
  • FIG. 6 illustrates yet another menu for entry of the fact type of FIG. 3; and
  • FIG. 7 illustrates how information in the template maps to the KRS structure.
  • FIG. 8 illustrates a schematic of a computer system that can be used to construct, maintain, query and populate a knowledge representation system.
  • DETAILED DESCRIPTION
  • A first embodiment comprises a method for deconstructing experimental findings originally occurring in narrative text or symbolic (e.g., graphical or tabular) documents, structuring and codifying these findings by means of templates and then storing the information contained in the completed templates in a KRS to create a KB.
  • The data architecture used in this embodiment is herein referred to as an ontology. An ontology is a hierarchical representation of the taxonomy and formal concepts and relationships relevant to the domain of interest stored in a knowledge representation system (“KRS”). In short, an ontology is a specific form of a KRS. The KRS may be a frame-based, rule-based or other type of database architecture, the choice of which may depend on a variety of factors, such as storage needs. In one embodiment, a frame-based KRS is used. Therefore, for purposes of describing the KRS of one embodiment, reference will be made to a frame-based KRS. However, it should be understood that other known types of data architecture may alternatively be used in connection with some embodiments, as will become apparent. In a first embodiment, the domain of interest is genomic information, which comprises at a minimum information relating to genes, their DNA sequences, the proteins which result when the genes are expressed, the biological effects of the expressed proteins and other, related information. Using an ontology allows searching to find relationships between and inferences about the items stored in the KB.
  • In order to accomplish these goals, the ontology must be formally defined and organized. The primary organizational component of the ontology in a frame-based KRS is the class. Classes are descriptions of particular categories of objects. Properties are attributes that describe the class itself or relate one class to another. An instance is an actual example of a class, and the relationship between two different instances in the ontology is defined by slots. Slots can be thought of as the verbs that relate and link two classes. Once information is represented in this manner, frame-based KRSs support basic inference capabilities such as classification and declarations of axioms. Axioms impose semantic constraints on the ontology that help to maintain the consistency and integrity of the data. Frame-based KRSs also provide basic query capabilities for retrieving stored data. Populating the frame-based KRS with real world examples of experimental information transforms the system into a KB.
  • FIG. 1 is a diagram of a portion of an ontology, illustrating the concepts of classes, properties and instances, as well as examples of experimental information that reside in the KB described herein. As shown in FIG. 1, ontology 10 has three sub-parts 15, 20 and 25. Sub-part 15 belongs to the class of interaction data and has three properties: effector, affected, and interaction type. Below sub-part 15 are sub-parts 20 and 25, respectively having the classes of phosphorylation assay and cell assay. Sub-parts 20 and 25 are both sub-classes of the class interaction data. Each sub-class inherits all the properties of its parent class. In the case of sub-class phosphorylation assay 20, an additional property of time-required is added. For the sub-class cell assay 25, the additional property added is reagents-used. Each sub-class shown in sub-parts 20 and 25 is shown linked to one instance of the respective subclass. Instance 30 is an instance of subclass 20 and instance 35 is an instance of subclass 25. The particular properties for instances 30 and 35 are filled in with actual values. Some of these values are examples of biological entities categorized and captured in other parts of the ontology. The effector PKC in instance 30 is an instance of a kinase, while the affected CREB is a transcription factor. Both the effector and affected are within the class of molecules and the subclass of proteins, as shown in molecule sub-ontology 40. In a similar fashion, in instance 35, the effector is IL-4, which is a member of the class cytokines, shown in sub-ontology 40, and the affected, B-Lymphocyte, is a lymphocytes in immune cells sub-ontology 45. The fact that the same object can belong to several different classes explains why searching across the KB can generate results that are not readily apparent from the individual items entered into it. Note that the illustrated ontology represents only a very small portion of the ontology that will be constructed using the methods of this first embodiment described herein.
  • The KB of various embodiments requires translating information from source text (e.g., information expressed in a natural language, such as English) and/or symbolic data (e.g., graphical or tabular data) into a computational information language. In the example used herein, the information is biological information, although it will be apparent to one skilled in the art that other types of information could be stored in a KB.
  • For purposes of this description, the process of translating information is called structuring knowledge, as it places knowledge, in this case biological findings, into the structure and architecture of the KRS. The method for structuring the knowledge is based on formalized models of experimental design and biological concepts. These models provide the framework for capturing a considerable portion of the loosely articulated findings typically found in academic literature. The specific level of experimental results that is of greatest value to industrial and academic scientists can be particularly targeted for capture. So, for example, in the field of genomics, knowledge that focuses on the effects that both perturbation to genes, gene products (RNA and proteins) and small molecules and various physical stimuli have upon biological systems is singled out. These perturbations and stimuli form the backbone of the KRS and provide the necessary framework for developing a more sophisticated representation of complex biological information.
  • Examples of the types of facts and biological relationships that can be translated into the KRS are: a) an increase in the amount of Fadd protein increases apoptosis; b) a decrease in Raf levels increases activation of Rip2; and c) the allele delta32 of CCR5, compared to the wild-type allele, decreases HIV transmission.
  • In one embodiment, biological systems are defined in terms of processes and objects. Discrete objects are physical things such as specific genes, proteins, cells and organisms. Processes are actions that act on those objects. Examples of processes include phosphorylation, which acts on discrete objects such as proteins, and apoptosis, which acts on cells. Perturbation of an object can have an effect on a process or on an object. Using these concepts of objects and processes, the information in the KB may be represented by a variety of fact types. In one embodiment, two distinct fact types of interest are: a) case-control facts; and b) observational facts.
  • A case-control fact describes those experimental results wherein a discrete object, such as a protein or a drug, or a specific physical stimulus, such as hypoxia, is added to a biological or biochemical system and the corresponding changes in the system are monitored and measured. An example of a case-control fact is, “expression of hRas from a viral vector increases the phosphorylation of MAPK in 293 cells.”
  • An observational fact reports an observation, not the alteration of a biological system by an effector. An example of an observational fact is, “examination of cells using laser scanning confocal microscopy revealed that Bcl-2 localizes to the mitochondria of 293 cells.”
  • In order to construct the KRS, each of these building blocks-objects, processes and experimental fact types, has been rigorously defined and characterized. Additionally, the KRS is able to store the appropriate details associated with all the processes (including process properties, modifiers and mediators), objects (including mutations, allele names and physical location). Capturing these details and creating varying levels of abstraction are necessary if the populated KB is to reflect the dynamic, complex and interconnected nature of biological findings.
  • FIGS. 2 a and 2 b illustrate how fact model types can be used to deconstruct the semantics of text-based information into its proper constituent components and then model and structure those components. In general, information to be extracted may exist in a text-based format, graphical form, or a combination of text and graphics. Typically, information is presented in both text and graphical form in a research article in the peer-reviewed literature. In the example illustrated in FIG. 2 a, a text paragraph 60 represents an experimental finding indicating that expression of a mutant form of the human protein Trf2 leads to increased frequency of chromosome end fusions, anaphase bridges and lagging chromosomes. As shown in FIG. 2 b, the fact of FIG. 2 a has been deconstructed. The fact is displayed at the left of the figure in colloquial form 71. Explicit semantic representation 73 of the fact is shown on the right of FIG. 2 b. Metadata 75 presents information related to the experiment from which the fact was derived. In this example, the metadata includes the type of experiment and the method used to visualize the experiment's results.
  • In order to maintain consistency in the deconstruction of the text-based (or symbolic) information and to insure that knowledge is acquired and structured in a manner strictly consistent with the KRS, fact templates have been designed and implemented. These templates are the tools used by scientists to take information extracted from source text, graphics, or a combination thereof, and to format that information so that it can be entered in the KRS. The templates may be accessible over the web and comprise a logical series of text boxes, with pull-down menus assigned to each text box. The content and configuration of these fact templates is driven by the content and fact model structure of the KRS. The templates are constructed to capture all fact types, relationships, objects and processes, as well as all associated details of these concepts, contained in the KRS. A scientist entering data into the templates cannot enter terms not contained in the KRS unless these new terms are marked as new and reviewed in the manner described below.
  • In the field of biological information, the first step in the process of knowledge entry is deciding on the type of fact being expressed by the information. For example, in one embodiment one needs to decide whether the fact is a case control fact or an observational type fact. The following example illustrates how a typical case control fact would be entered into a template and then stored in the KRS. FIG. 3 shows the flow structure depicting the deconstruction and modeling of a simplified case control fact into its constituent components for entry into the KRS. As shown in FIG. 3, case control fact 101 comprises an effector 103 which causes a change of direction 105 to a property 107 of an object 109.
  • A specific example of a case control fact, “. . . in 293 cells, transient overexpression of mouse (mus) Fas induced apoptosis in a dose-dependent manner,” has an effector (the protein Fas) which causes a change (induction) of a property (apoptosis) in an object (293 cells). These components of a case control fact are correspondingly represented and modeled by the appropriate template with the appropriate pull-down menus.
  • In this example, the scientist would first call up the case control template. FIG. 4 illustrates how the appropriate case control template would initially appear to the scientist. After choosing the case control template, the image shown in FIG. 4 is displayed. As the template displays a menu box 111 for protein and cellular process, the scientist knows that the correct template has been chosen for this particular example, as a protein effector Fas has been shown to cause a change in a cellular process, here apoptosis. Several different but similar templates are used for other modifications of case control facts, observational fact, or other fact types.
  • The initial basic information that is entered into the fact type template automatically dictates the next frame that will be shown to the scientist to capture all details of a given fact. In this particular example, as shown in FIG. 5, the scientist is prompted to provide further information on the protein involved. The scientist is first provided with a text box 112 that allows entry of a few letters of the effector name (in the example given, the scientist could type an F, fas, mus, etc.) and possible exact matches will be presented in a drop down list. As shown in FIG. 5, the appropriate selection in this example is Fas mouse (mus) protein.
  • In each series of frames the scientist is presented with text boxes and associated pull-down menus, which offer constrained choices for entering the main components of the fact-properties, objects and their associated details, as defined by the KRS. As an alternative to pull-down menus, the user could be presented with a type-in field. In this embodiment, the user input would be checked against a predefined list of information choices acceptable to the fact type. In still another embodiment, a user could be presented with icons for selecting valid field values.
  • The next step in this example is to enter any details associated with the Fas mouse protein. Access to additional menus for specified details of an object is enabled by clicking on a “details” button.
  • In this example, there is one detail to enter, the instance that Fas was in a specified location (293 cells) while inducing apoptosis. As shown in FIG. 6, pressing the “get details” button 151 automatically brings up a drop down list of constrained terms from the KRS for the scientist to choose from. From the presented drop down list, the scientist would select “293 cell line” in the “has_physical_location” box to specify the exact object involved. This process is continued to capture all the details associated with the given fact. In this example, details include the direction of change (an increase), the fact that this change occurred in a dose dependent manner and the particular cellular process, apoptosis, occurred in 293 cells. Thus, as illustrated in this example, by presenting the scientist with a set of fact templates that are comprised of a constrained representation of fact types, restricted language choices and only appropriate selection menus which are fully consistent with the architecture and dictionary of the KRS, various embodiments ensure that information is structured in a way that is consistent with the hierarchical organization and controlled vocabulary of the KRS.
  • FIG. 7 is an illustration of how a completed fact template maps graphically to the data architecture of the KRS.
  • For those situations when new concepts and terms not already represented in the KRS are discovered and must be represented in the KRS, a new item slot is made available within the template for the user to insert the new term. The new item slot appears when the term is not presented in the templates or if the term, after being typed into a text box, is not recognized by the KRS. Entries made into the new item slot are automatically flagged and later evaluated by KEs for incorporation within the KRS.
  • The use of the fact templates allows various embodiments to acquire knowledge for the KRS that is structured completely in accordance with instances already within the KRS, to express distinct types of experimental propositions in distinct fact structures, to ascribe standardized meanings for each component of the sentences of text-based information to be incorporated with the KRS, to utilize absolutely consistent terminology and to utilize concepts at distinct but interrelated levels of abstraction. As scientists can with relative ease acquire the skill to complete these templates and as the information in a properly completed template can be readily incorporated into the KRS to generate a populated KB, the KB can be expanded very rapidly, with only occasional intervention by the KEs when new concepts and terms are found.
  • Various embodiments' methods for rapidly populating a KRS, although described in the particular field of genomics, can be readily applied to all fields wherein the body of knowledge is rapidly growing. Possible other fields of knowledge where various embodiments could be applied to organize that knowledge are geology, particularly information relating to potential oilfield structure, as this generally comprises huge data sets, meteorology and ecology. This list of alternative fields of knowledge is not intended to be exclusive.
  • As shown in FIG. 8, some embodiments include code on a computer readable medium. The computer readable medium can be one or a combination of memory 803, processor 801, hard disk, CD 811, DVD 812, floppy, and/or carrier wave traveling a wired and/or wireless network 805, etc.

Claims (13)

1-12. (canceled)
13. A frame-based Knowledge Representation System (KRS) populated with facts, the facts having been entered into the system by the step of:
transferring a plurality of structured facts from completed fact templates KRS to form a knowledge base, the structured facts being derived from natural language information sources;
wherein the KRS is an ontology having varying levels of abstraction of biological concepts and the structured facts correspond to one or more of the varying levels of abstraction.
14. The KRS of claim 13 wherein the natural language information sources comprise at least one of text-based and symbolic biological information sources.
15. The KRS of claim 13 wherein the fact templates structure and constrain a fact extracted from the information sources according to a user interface that constrains user data entry based upon a set of valid entries consistent with the structure and content of the ontology.
16. The KRS of claim 15 wherein the user interface includes a blank menu option, the blank menu option permitting the input of a new information choice not offered by the set of valid user entries.
17. The KRS of claim 16 wherein all competed templates in which a blank menu option was selected are reviewed prior to transferring the fact and the ontology is modified to accept the new information choice if a reviewer of the fact approves the new information choice.
18. The KRS of claim 17 wherein the templates are completed by experts knowledgeable in the field represented by the ontology and the review of new information choices is conducted by the experts and knowledge base engineers.
19. Fact templates for use in a Knowledge Representation System (KRS) comprising:
at least one fact-type specific fact template, each fact-type specific fact template accepting one predefined fact type found in predetermined information sources wherein the template translates the fact type from one of a text-based, graphical and tabular language into a computational information language of the KRS; and
the at least one fact-type specific fact template having at least one user interface that constrains user data entry to one of a predetermined set of valid user entries that may be inserted into the fact template at the user interface.
20. The fact templates of claim 19 wherein scientists expert in the field defined by the predetermined information sources extract information from the predetermined information sources and complete the templates with the extracted information.
21. The fact templates of claim 20 wherein the user interface includes a user entry field that permits entry of new information not included in the predetermined set of valid user entries.
22. The fact templates of claim 21 wherein information entered into the user entry field automatically flags the completed fact template for review.
23. The fact templates of claim 22 wherein the ontology is modified to accept the new information if the fact template passes review.
24-38. (canceled)
US12/499,761 2000-06-08 2009-07-08 Computerized knowledge representation system with flexible user entry fields Expired - Lifetime US8392353B2 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US12/499,761 US8392353B2 (en) 2000-06-08 2009-07-08 Computerized knowledge representation system with flexible user entry fields
US13/745,605 US9514408B2 (en) 2000-06-08 2013-01-18 Constructing and maintaining a computerized knowledge representation system using fact templates

Applications Claiming Priority (9)

Application Number Priority Date Filing Date Title
US21089800P 2000-06-08 2000-06-08
US22942400P 2000-08-31 2000-08-31
US22958200P 2000-08-31 2000-08-31
US22939200P 2000-08-31 2000-08-31
US22958100P 2000-08-31 2000-08-31
US09/733,495 US6772160B2 (en) 2000-06-08 2000-12-08 Techniques for facilitating information acquisition and storage
US10/038,197 US6741986B2 (en) 2000-12-08 2001-11-09 Method and system for performing information extraction and quality control for a knowledgebase
US10/770,864 US7577683B2 (en) 2000-06-08 2004-02-02 Methods for the construction and maintenance of a knowledge representation system
US12/499,761 US8392353B2 (en) 2000-06-08 2009-07-08 Computerized knowledge representation system with flexible user entry fields

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US10/770,864 Division US7577683B2 (en) 2000-06-08 2004-02-02 Methods for the construction and maintenance of a knowledge representation system

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US13/745,605 Continuation US9514408B2 (en) 2000-06-08 2013-01-18 Constructing and maintaining a computerized knowledge representation system using fact templates

Publications (2)

Publication Number Publication Date
US20100010957A1 true US20100010957A1 (en) 2010-01-14
US8392353B2 US8392353B2 (en) 2013-03-05

Family

ID=42562599

Family Applications (3)

Application Number Title Priority Date Filing Date
US10/770,864 Expired - Lifetime US7577683B2 (en) 2000-06-08 2004-02-02 Methods for the construction and maintenance of a knowledge representation system
US12/499,761 Expired - Lifetime US8392353B2 (en) 2000-06-08 2009-07-08 Computerized knowledge representation system with flexible user entry fields
US13/745,605 Expired - Lifetime US9514408B2 (en) 2000-06-08 2013-01-18 Constructing and maintaining a computerized knowledge representation system using fact templates

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US10/770,864 Expired - Lifetime US7577683B2 (en) 2000-06-08 2004-02-02 Methods for the construction and maintenance of a knowledge representation system

Family Applications After (1)

Application Number Title Priority Date Filing Date
US13/745,605 Expired - Lifetime US9514408B2 (en) 2000-06-08 2013-01-18 Constructing and maintaining a computerized knowledge representation system using fact templates

Country Status (1)

Country Link
US (3) US7577683B2 (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060036368A1 (en) * 2002-02-04 2006-02-16 Ingenuity Systems, Inc. Drug discovery methods
US20070178473A1 (en) * 2002-02-04 2007-08-02 Chen Richard O Drug discovery methods
US20080033819A1 (en) * 2006-07-28 2008-02-07 Ingenuity Systems, Inc. Genomics based targeted advertising
US20110191286A1 (en) * 2000-12-08 2011-08-04 Cho Raymond J Method And System For Performing Information Extraction And Quality Control For A Knowledge Base
US9335991B1 (en) 2015-09-18 2016-05-10 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US9372684B1 (en) * 2015-09-18 2016-06-21 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US9514408B2 (en) 2000-06-08 2016-12-06 Ingenuity Systems, Inc. Constructing and maintaining a computerized knowledge representation system using fact templates
US9552200B1 (en) 2015-09-18 2017-01-24 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US9600625B2 (en) 2012-04-23 2017-03-21 Bina Technologies, Inc. Systems and methods for processing nucleic acid sequence data
US9864598B2 (en) 2015-09-18 2018-01-09 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program
US11157260B2 (en) 2015-09-18 2021-10-26 ReactiveCore LLC Efficient information storage and retrieval using subgraphs

Families Citing this family (48)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6772160B2 (en) * 2000-06-08 2004-08-03 Ingenuity Systems, Inc. Techniques for facilitating information acquisition and storage
US7013308B1 (en) 2000-11-28 2006-03-14 Semscript Ltd. Knowledge storage and retrieval system and method
FR2887353B1 (en) * 2005-06-21 2007-09-07 Denis Pierre "METHOD AND SYSTEM FOR BUILDING A LANGUAGE OF A KNOWLEDGE BASE"
US8666928B2 (en) 2005-08-01 2014-03-04 Evi Technologies Limited Knowledge repository
US8495004B2 (en) * 2006-03-27 2013-07-23 International Business Machines Corporation Determining and storing at least one results set in a global ontology database for future use by an entity that subscribes to the global ontology database
US7860815B1 (en) * 2006-07-12 2010-12-28 Venkateswara Prasad Tangirala Computer knowledge representation format, system, methods, and applications
US9495358B2 (en) 2006-10-10 2016-11-15 Abbyy Infopoisk Llc Cross-language text clustering
US20080301120A1 (en) * 2007-06-04 2008-12-04 Precipia Systems Inc. Method, apparatus and computer program for managing the processing of extracted data
US8838659B2 (en) 2007-10-04 2014-09-16 Amazon Technologies, Inc. Enhanced knowledge repository
US7996719B2 (en) * 2008-10-24 2011-08-09 Microsoft Corporation Expressing fault correlation constraints
US9805089B2 (en) 2009-02-10 2017-10-31 Amazon Technologies, Inc. Local business and product search system and method
US20150309316A1 (en) 2011-04-06 2015-10-29 Microsoft Technology Licensing, Llc Ar glasses with predictive control of external device based on event input
US9223134B2 (en) 2010-02-28 2015-12-29 Microsoft Technology Licensing, Llc Optical imperfections in a light transmissive illumination system for see-through near-eye display glasses
US10180572B2 (en) 2010-02-28 2019-01-15 Microsoft Technology Licensing, Llc AR glasses with event and user action control of external applications
US9182596B2 (en) 2010-02-28 2015-11-10 Microsoft Technology Licensing, Llc See-through near-eye display glasses with the optical assembly including absorptive polarizers or anti-reflective coatings to reduce stray light
US9097891B2 (en) 2010-02-28 2015-08-04 Microsoft Technology Licensing, Llc See-through near-eye display glasses including an auto-brightness control for the display brightness based on the brightness in the environment
US9091851B2 (en) 2010-02-28 2015-07-28 Microsoft Technology Licensing, Llc Light control in head mounted displays
US9759917B2 (en) 2010-02-28 2017-09-12 Microsoft Technology Licensing, Llc AR glasses with event and sensor triggered AR eyepiece interface to external devices
US9097890B2 (en) 2010-02-28 2015-08-04 Microsoft Technology Licensing, Llc Grating in a light transmissive illumination system for see-through near-eye display glasses
US9129295B2 (en) 2010-02-28 2015-09-08 Microsoft Technology Licensing, Llc See-through near-eye display glasses with a fast response photochromic film system for quick transition from dark to clear
US9128281B2 (en) 2010-09-14 2015-09-08 Microsoft Technology Licensing, Llc Eyepiece with uniformly illuminated reflective display
EP2539759A1 (en) 2010-02-28 2013-01-02 Osterhout Group, Inc. Local advertising content on an interactive head-mounted eyepiece
US9134534B2 (en) 2010-02-28 2015-09-15 Microsoft Technology Licensing, Llc See-through near-eye display glasses including a modular image source
US9366862B2 (en) 2010-02-28 2016-06-14 Microsoft Technology Licensing, Llc System and method for delivering content to a group of see-through near eye display eyepieces
US9229227B2 (en) 2010-02-28 2016-01-05 Microsoft Technology Licensing, Llc See-through near-eye display glasses with a light transmissive wedge shaped illumination system
US20120249797A1 (en) 2010-02-28 2012-10-04 Osterhout Group, Inc. Head-worn adaptive display
US9341843B2 (en) 2010-02-28 2016-05-17 Microsoft Technology Licensing, Llc See-through near-eye display glasses with a small scale image source
US9285589B2 (en) 2010-02-28 2016-03-15 Microsoft Technology Licensing, Llc AR glasses with event and sensor triggered control of AR eyepiece applications
US9110882B2 (en) 2010-05-14 2015-08-18 Amazon Technologies, Inc. Extracting structured knowledge from unstructured text
US9053182B2 (en) * 2011-01-27 2015-06-09 International Business Machines Corporation System and method for making user generated audio content on the spoken web navigable by community tagging
US9773091B2 (en) 2011-10-31 2017-09-26 The Scripps Research Institute Systems and methods for genomic annotation and distributed variant interpretation
CN104094266A (en) 2011-11-07 2014-10-08 独创系统公司 Methods and systems for identification of causal genomic variants
US8725774B2 (en) * 2012-10-05 2014-05-13 Xerox Corporation Enforcing policies over linked XML resources
US9418203B2 (en) 2013-03-15 2016-08-16 Cypher Genomics, Inc. Systems and methods for genomic variant annotation
US11342048B2 (en) 2013-03-15 2022-05-24 The Scripps Research Institute Systems and methods for genomic annotation and distributed variant interpretation
CA2942811A1 (en) 2013-03-15 2014-09-25 The Scripps Research Institute Systems and methods for genomic annotation and distributed variant interpretation
WO2015027085A1 (en) 2013-08-22 2015-02-26 Genomoncology, Llc Computer-based systems and methods for analyzing genomes based on discrete data structures corresponding to genetic variants therein
RU2586577C2 (en) 2014-01-15 2016-06-10 Общество с ограниченной ответственностью "Аби ИнфоПоиск" Filtering arcs parser graph
BR112016018547B1 (en) 2014-02-13 2023-12-12 Illumina, Inc METHOD FOR PROCESSING GENOMIC INFORMATION
US9626358B2 (en) 2014-11-26 2017-04-18 Abbyy Infopoisk Llc Creating ontologies by analyzing natural language texts
CA2982169A1 (en) 2015-04-10 2016-10-13 Applied Proteomics, Inc. Protein biomarker panels for detecting colorectal cancer and advanced adenoma
US10970634B2 (en) 2016-11-10 2021-04-06 General Electric Company Methods and systems for capturing analytic model authoring knowledge
US11380420B1 (en) * 2018-05-07 2022-07-05 X Development Llc Data structure, compilation service, and graphical user interface for rapid simulation generation
CN110555528A (en) * 2018-05-31 2019-12-10 福建天泉教育科技有限公司 knowledge system construction method based on template and terminal
US11170031B2 (en) 2018-08-31 2021-11-09 International Business Machines Corporation Extraction and normalization of mutant genes from unstructured text for cognitive search and analytics
US11036774B2 (en) * 2018-10-04 2021-06-15 Robert Bosch Gmbh Knowledge-based question answering system for the DIY domain
WO2020236799A1 (en) * 2019-05-20 2020-11-26 Schlumberger Technology Corporation Automated system and method for processing oilfield information
US11334541B1 (en) 2020-07-17 2022-05-17 Rainer Michael Domingo Knowledge representation using interlinked construct nodes

Citations (47)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5317507A (en) * 1990-11-07 1994-05-31 Gallant Stephen I Method for document retrieval and for word sense disambiguation using neural networks
US5371807A (en) * 1992-03-20 1994-12-06 Digital Equipment Corporation Method and apparatus for text classification
US5377103A (en) * 1992-05-15 1994-12-27 International Business Machines Corporation Constrained natural language interface for a computer that employs a browse function
US5398183A (en) * 1990-12-10 1995-03-14 Biomedical Systems Corporation Holter ECG report generating system
US5418971A (en) * 1992-04-20 1995-05-23 International Business Machines Corporation System and method for ordering commands in an automatic volume placement library
US5625814A (en) * 1992-05-27 1997-04-29 Apple Computer, Inc. Method and apparatus for processing natural language with a hierarchy of mapping routines
US5625721A (en) * 1992-10-09 1997-04-29 Matsushita Information Technology Laboratory Certifiable optical character recognition
US5794050A (en) * 1995-01-04 1998-08-11 Intelligent Text Processing, Inc. Natural language understanding system
US5963966A (en) * 1995-11-08 1999-10-05 Cybernet Systems Corporation Automated capture of technical documents for electronic review and distribution
US5976842A (en) * 1997-10-30 1999-11-02 Clontech Laboratories, Inc. Methods and compositions for use in high fidelity polymerase chain reaction
US6023659A (en) * 1996-10-10 2000-02-08 Incyte Pharmaceuticals, Inc. Database system employing protein function hierarchies for viewing biomolecular sequence data
US6038560A (en) * 1997-05-21 2000-03-14 Oracle Corporation Concept knowledge base search and retrieval system
US6052714A (en) * 1995-12-14 2000-04-18 Kabushiki Kaisha Toshiba Information filtering apparatus and method for retrieving a selected article from information sources
US6067548A (en) * 1998-07-16 2000-05-23 E Guanxi, Inc. Dynamic organization model and management computing system and method therefor
US6101488A (en) * 1996-09-04 2000-08-08 Fujitsu Limited Intelligent information program generation and retrieval system
US6115640A (en) * 1997-01-17 2000-09-05 Nec Corporation Workflow system for rearrangement of a workflow according to the progress of a work and its workflow management method
US6154737A (en) * 1996-05-29 2000-11-28 Matsushita Electric Industrial Co., Ltd. Document retrieval system
US6226377B1 (en) * 1998-03-06 2001-05-01 Avaya Technology Corp. Prioritized transaction server allocation
US6236987B1 (en) * 1998-04-03 2001-05-22 Damon Horowitz Dynamic content organization in information retrieval systems
US6263335B1 (en) * 1996-02-09 2001-07-17 Textwise Llc Information extraction system and method using concept-relation-concept (CRC) triples
US6292796B1 (en) * 1999-02-23 2001-09-18 Clinical Focus, Inc. Method and apparatus for improving access to literature
US6308170B1 (en) * 1997-07-25 2001-10-23 Affymetrix Inc. Gene expression and evaluation system
US20010049671A1 (en) * 2000-06-05 2001-12-06 Joerg Werner B. e-Stract: a process for knowledge-based retrieval of electronic information
US6345235B1 (en) * 1997-05-30 2002-02-05 Queen's University At Kingston Method and apparatus for determining multi-dimensional structure
US6370542B1 (en) * 1998-10-23 2002-04-09 Qwest Communications International, Inc. Method and apparatus for knowledge acquisition and management
US6424980B1 (en) * 1998-06-10 2002-07-23 Nippon Telegraph And Telephone Corporation Integrated retrieval scheme for retrieving semi-structured documents
US6442566B1 (en) * 1998-12-15 2002-08-27 Board Of Trustees Of The Leland Stanford Junior University Frame-based knowledge representation system and methods
US6470277B1 (en) * 1999-07-30 2002-10-22 Agy Therapeutics, Inc. Techniques for facilitating identification of candidate genes
US20020165737A1 (en) * 1999-03-15 2002-11-07 Nexcura, Inc. Automated profiler system for providing medical information to patients
US6487545B1 (en) * 1995-05-31 2002-11-26 Oracle Corporation Methods and apparatus for classifying terminology utilizing a knowledge catalog
US20020194201A1 (en) * 2001-06-05 2002-12-19 Wilbanks John Thompson Systems, methods and computer program products for integrating biological/chemical databases to create an ontology network
US6498795B1 (en) * 1998-11-18 2002-12-24 Nec Usa Inc. Method and apparatus for active information discovery and retrieval
US20030018522A1 (en) * 2001-07-20 2003-01-23 Psc Scanning, Inc. Biometric system and method for identifying a customer upon entering a retail establishment
US6598043B1 (en) * 1999-10-04 2003-07-22 Jarg Corporation Classification of information sources using graph structures
US20040036368A1 (en) * 2002-08-26 2004-02-26 Transpo Electronics, Inc. Integrally formed rectifier for internal alternator regulator (IAR) style alternator
US6741976B1 (en) * 1999-07-01 2004-05-25 Alexander Tuzhilin Method and system for the creation, application and processing of logical rules in connection with biological, medical or biochemical data
US6741986B2 (en) * 2000-12-08 2004-05-25 Ingenuity Systems, Inc. Method and system for performing information extraction and quality control for a knowledgebase
US6772160B2 (en) * 2000-06-08 2004-08-03 Ingenuity Systems, Inc. Techniques for facilitating information acquisition and storage
US20040220969A1 (en) * 2000-06-08 2004-11-04 Ingenuity Systems, Inc., A Delaware Corporation Methods for the construction and maintenance of a knowledge representation system
US20040249620A1 (en) * 2002-11-20 2004-12-09 Genstruct, Inc. Epistemic engine
US6904423B1 (en) * 1999-02-19 2005-06-07 Bioreason, Inc. Method and system for artificial intelligence directed lead discovery through multi-domain clustering
US20060064037A1 (en) * 2004-09-22 2006-03-23 Shalon Ventures Research, Llc Systems and methods for monitoring and modifying behavior
US7022905B1 (en) * 1999-10-18 2006-04-04 Microsoft Corporation Classification of information and use of classifications in searching and retrieval of information
US20060143082A1 (en) * 2004-12-24 2006-06-29 Peter Ebert Advertisement system and method
US20070028632A1 (en) * 2005-08-03 2007-02-08 Mingsheng Liu Chiller control system and method
US20080033819A1 (en) * 2006-07-28 2008-02-07 Ingenuity Systems, Inc. Genomics based targeted advertising
US20080255877A1 (en) * 1999-11-06 2008-10-16 Fernandez Dennis S Bioinformatic Transaction Scheme

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB9222884D0 (en) * 1992-10-30 1992-12-16 Massachusetts Inst Technology System for administration of privatization in newly democratic nations
US5644686A (en) * 1994-04-29 1997-07-01 International Business Machines Corporation Expert system and method employing hierarchical knowledge base, and interactive multimedia/hypermedia applications
US5980096A (en) * 1995-01-17 1999-11-09 Intertech Ventures, Ltd. Computer-based system, methods and graphical interface for information storage, modeling and stimulation of complex systems
US6554705B1 (en) 1997-08-22 2003-04-29 Blake Cumbers Passive biometric customer identification and tracking system
KR100269258B1 (en) * 1997-10-21 2000-10-16 정선종 Integrated CASE Information Repository Metamodel System for Process Methodology and its Integration Support Method
US6055538A (en) 1997-12-22 2000-04-25 Hewlett Packard Company Methods and system for using web browser to search large collections of documents
JP3597370B2 (en) 1998-03-10 2004-12-08 富士通株式会社 Document processing device and recording medium
JP2001134600A (en) 1999-11-08 2001-05-18 Nec Corp System and method for information extraction and recording medium stored with recorded program for information extraction
EP1158447A1 (en) 2000-05-26 2001-11-28 GMD- Forschungszentrum Informationstechnik GmbH Method for evaluating states of biological systems
JP2003521071A (en) 2000-01-27 2003-07-08 インフォーマックス、インコーポレイテッド Integrated access to biomedical resources
US20030171876A1 (en) 2002-03-05 2003-09-11 Victor Markowitz System and method for managing gene expression data
AU2003207786B2 (en) 2002-02-04 2009-09-17 QIAGEN Redwood City, Inc. Drug discovery methods
US8793073B2 (en) 2002-02-04 2014-07-29 Ingenuity Systems, Inc. Drug discovery methods
US7865534B2 (en) 2002-09-30 2011-01-04 Genstruct, Inc. System, method and apparatus for assembling and mining life science data
EP1639087A4 (en) 2003-06-25 2008-12-24 Smithkline Beecham Corp Biological data set comparison method
US7505989B2 (en) 2004-09-03 2009-03-17 Biowisdom Limited System and method for creating customized ontologies
US20070282632A1 (en) 2006-05-30 2007-12-06 Eric Sachs Method and apparatus for serving advertisements in an electronic medical record system
US8140270B2 (en) 2007-03-22 2012-03-20 National Center For Genome Resources Methods and systems for medical sequencing analysis
US20110098193A1 (en) 2009-10-22 2011-04-28 Kingsmore Stephen F Methods and Systems for Medical Sequencing Analysis

Patent Citations (51)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5317507A (en) * 1990-11-07 1994-05-31 Gallant Stephen I Method for document retrieval and for word sense disambiguation using neural networks
US5398183A (en) * 1990-12-10 1995-03-14 Biomedical Systems Corporation Holter ECG report generating system
US5371807A (en) * 1992-03-20 1994-12-06 Digital Equipment Corporation Method and apparatus for text classification
US5418971A (en) * 1992-04-20 1995-05-23 International Business Machines Corporation System and method for ordering commands in an automatic volume placement library
US5377103A (en) * 1992-05-15 1994-12-27 International Business Machines Corporation Constrained natural language interface for a computer that employs a browse function
US5625814A (en) * 1992-05-27 1997-04-29 Apple Computer, Inc. Method and apparatus for processing natural language with a hierarchy of mapping routines
US5625721A (en) * 1992-10-09 1997-04-29 Matsushita Information Technology Laboratory Certifiable optical character recognition
US5794050A (en) * 1995-01-04 1998-08-11 Intelligent Text Processing, Inc. Natural language understanding system
US6487545B1 (en) * 1995-05-31 2002-11-26 Oracle Corporation Methods and apparatus for classifying terminology utilizing a knowledge catalog
US5963966A (en) * 1995-11-08 1999-10-05 Cybernet Systems Corporation Automated capture of technical documents for electronic review and distribution
US6052714A (en) * 1995-12-14 2000-04-18 Kabushiki Kaisha Toshiba Information filtering apparatus and method for retrieving a selected article from information sources
US6263335B1 (en) * 1996-02-09 2001-07-17 Textwise Llc Information extraction system and method using concept-relation-concept (CRC) triples
US6154737A (en) * 1996-05-29 2000-11-28 Matsushita Electric Industrial Co., Ltd. Document retrieval system
US6101488A (en) * 1996-09-04 2000-08-08 Fujitsu Limited Intelligent information program generation and retrieval system
US6023659A (en) * 1996-10-10 2000-02-08 Incyte Pharmaceuticals, Inc. Database system employing protein function hierarchies for viewing biomolecular sequence data
US6115640A (en) * 1997-01-17 2000-09-05 Nec Corporation Workflow system for rearrangement of a workflow according to the progress of a work and its workflow management method
US6038560A (en) * 1997-05-21 2000-03-14 Oracle Corporation Concept knowledge base search and retrieval system
US6345235B1 (en) * 1997-05-30 2002-02-05 Queen's University At Kingston Method and apparatus for determining multi-dimensional structure
US6308170B1 (en) * 1997-07-25 2001-10-23 Affymetrix Inc. Gene expression and evaluation system
US5976842A (en) * 1997-10-30 1999-11-02 Clontech Laboratories, Inc. Methods and compositions for use in high fidelity polymerase chain reaction
US6226377B1 (en) * 1998-03-06 2001-05-01 Avaya Technology Corp. Prioritized transaction server allocation
US6236987B1 (en) * 1998-04-03 2001-05-22 Damon Horowitz Dynamic content organization in information retrieval systems
US6424980B1 (en) * 1998-06-10 2002-07-23 Nippon Telegraph And Telephone Corporation Integrated retrieval scheme for retrieving semi-structured documents
US6067548A (en) * 1998-07-16 2000-05-23 E Guanxi, Inc. Dynamic organization model and management computing system and method therefor
US6370542B1 (en) * 1998-10-23 2002-04-09 Qwest Communications International, Inc. Method and apparatus for knowledge acquisition and management
US6498795B1 (en) * 1998-11-18 2002-12-24 Nec Usa Inc. Method and apparatus for active information discovery and retrieval
US6442566B1 (en) * 1998-12-15 2002-08-27 Board Of Trustees Of The Leland Stanford Junior University Frame-based knowledge representation system and methods
US6904423B1 (en) * 1999-02-19 2005-06-07 Bioreason, Inc. Method and system for artificial intelligence directed lead discovery through multi-domain clustering
US6292796B1 (en) * 1999-02-23 2001-09-18 Clinical Focus, Inc. Method and apparatus for improving access to literature
US20020165737A1 (en) * 1999-03-15 2002-11-07 Nexcura, Inc. Automated profiler system for providing medical information to patients
US6741976B1 (en) * 1999-07-01 2004-05-25 Alexander Tuzhilin Method and system for the creation, application and processing of logical rules in connection with biological, medical or biochemical data
US6470277B1 (en) * 1999-07-30 2002-10-22 Agy Therapeutics, Inc. Techniques for facilitating identification of candidate genes
US6598043B1 (en) * 1999-10-04 2003-07-22 Jarg Corporation Classification of information sources using graph structures
US7022905B1 (en) * 1999-10-18 2006-04-04 Microsoft Corporation Classification of information and use of classifications in searching and retrieval of information
US20080255877A1 (en) * 1999-11-06 2008-10-16 Fernandez Dennis S Bioinformatic Transaction Scheme
US20010049671A1 (en) * 2000-06-05 2001-12-06 Joerg Werner B. e-Stract: a process for knowledge-based retrieval of electronic information
US6772160B2 (en) * 2000-06-08 2004-08-03 Ingenuity Systems, Inc. Techniques for facilitating information acquisition and storage
US20040220969A1 (en) * 2000-06-08 2004-11-04 Ingenuity Systems, Inc., A Delaware Corporation Methods for the construction and maintenance of a knowledge representation system
US20050044071A1 (en) * 2000-06-08 2005-02-24 Ingenuity Systems, Inc. Techniques for facilitating information acquisition and storage
US20110191286A1 (en) * 2000-12-08 2011-08-04 Cho Raymond J Method And System For Performing Information Extraction And Quality Control For A Knowledge Base
US6741986B2 (en) * 2000-12-08 2004-05-25 Ingenuity Systems, Inc. Method and system for performing information extraction and quality control for a knowledgebase
US20040236740A1 (en) * 2000-12-08 2004-11-25 Ingenuity Systems, Inc. Method and system for performing information extraction and quality control for a knowledgebase
US20050055347A9 (en) * 2000-12-08 2005-03-10 Ingenuity Systems, Inc. Method and system for performing information extraction and quality control for a knowledgebase
US20020194201A1 (en) * 2001-06-05 2002-12-19 Wilbanks John Thompson Systems, methods and computer program products for integrating biological/chemical databases to create an ontology network
US20030018522A1 (en) * 2001-07-20 2003-01-23 Psc Scanning, Inc. Biometric system and method for identifying a customer upon entering a retail establishment
US20040036368A1 (en) * 2002-08-26 2004-02-26 Transpo Electronics, Inc. Integrally formed rectifier for internal alternator regulator (IAR) style alternator
US20040249620A1 (en) * 2002-11-20 2004-12-09 Genstruct, Inc. Epistemic engine
US20060064037A1 (en) * 2004-09-22 2006-03-23 Shalon Ventures Research, Llc Systems and methods for monitoring and modifying behavior
US20060143082A1 (en) * 2004-12-24 2006-06-29 Peter Ebert Advertisement system and method
US20070028632A1 (en) * 2005-08-03 2007-02-08 Mingsheng Liu Chiller control system and method
US20080033819A1 (en) * 2006-07-28 2008-02-07 Ingenuity Systems, Inc. Genomics based targeted advertising

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
'An object oriented and constraint based knowledge representation system for design object modeling': Yokoyama, 1990, IEEE, CH2842-3, pp146-152 *
'Object oriented design and programming with C++': Leach, 1995, AP Professional, ISBN 0-12-440215-1 *

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9514408B2 (en) 2000-06-08 2016-12-06 Ingenuity Systems, Inc. Constructing and maintaining a computerized knowledge representation system using fact templates
US20110191286A1 (en) * 2000-12-08 2011-08-04 Cho Raymond J Method And System For Performing Information Extraction And Quality Control For A Knowledge Base
US20070178473A1 (en) * 2002-02-04 2007-08-02 Chen Richard O Drug discovery methods
US8489334B2 (en) 2002-02-04 2013-07-16 Ingenuity Systems, Inc. Drug discovery methods
US8793073B2 (en) 2002-02-04 2014-07-29 Ingenuity Systems, Inc. Drug discovery methods
US10453553B2 (en) 2002-02-04 2019-10-22 QIAGEN Redwood City, Inc. Drug discovery methods
US10006148B2 (en) 2002-02-04 2018-06-26 QIAGEN Redwood City, Inc. Drug discovery methods
US20060036368A1 (en) * 2002-02-04 2006-02-16 Ingenuity Systems, Inc. Drug discovery methods
US20080033819A1 (en) * 2006-07-28 2008-02-07 Ingenuity Systems, Inc. Genomics based targeted advertising
US9600625B2 (en) 2012-04-23 2017-03-21 Bina Technologies, Inc. Systems and methods for processing nucleic acid sequence data
US20170147332A1 (en) * 2015-09-18 2017-05-25 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program
US9372684B1 (en) * 2015-09-18 2016-06-21 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US9552200B1 (en) 2015-09-18 2017-01-24 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US9703549B2 (en) 2015-09-18 2017-07-11 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US9766879B2 (en) 2015-09-18 2017-09-19 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US9798538B2 (en) * 2015-09-18 2017-10-24 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program
US9864598B2 (en) 2015-09-18 2018-01-09 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program
US9588759B1 (en) 2015-09-18 2017-03-07 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US10152319B2 (en) 2015-09-18 2018-12-11 ReactiveCore LLP System and method for providing supplemental functionalities to a computer program via an ontology instance
US10223100B2 (en) 2015-09-18 2019-03-05 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US10346154B2 (en) 2015-09-18 2019-07-09 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program
US10387143B2 (en) 2015-09-18 2019-08-20 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program
US9335991B1 (en) 2015-09-18 2016-05-10 ReactiveCore LLC System and method for providing supplemental functionalities to a computer program via an ontology instance
US11157260B2 (en) 2015-09-18 2021-10-26 ReactiveCore LLC Efficient information storage and retrieval using subgraphs

Also Published As

Publication number Publication date
US8392353B2 (en) 2013-03-05
US9514408B2 (en) 2016-12-06
US20140019404A1 (en) 2014-01-16
US20040220969A1 (en) 2004-11-04
US7577683B2 (en) 2009-08-18

Similar Documents

Publication Publication Date Title
US8392353B2 (en) Computerized knowledge representation system with flexible user entry fields
Soibelman et al. Management and analysis of unstructured construction data types
Ur-Rahman et al. Textual data mining for industrial knowledge management and text classification: A business oriented approach
US8494987B2 (en) Semantic relationship extraction, text categorization and hypothesis generation
Leontis et al. The RNA Ontology Consortium: an open invitation to the RNA community
WO2009038788A1 (en) Method and system for active learning screening process with dynamic information modeling
Cui et al. Introducing Explorer of Taxon Concepts with a case study on spider measurement matrix building
Dobson Interpretable outputs: criteria for machine learning in the humanities
Aladakatti et al. Exploring natural language processing techniques to extract semantics from unstructured dataset which will aid in effective semantic interlinking
Gelman et al. A language-agnostic model for semantic source code labeling
Atkinson-Abutridy Text Analytics: An Introduction to the Science and Applications of Unstructured Information Analysis
Li et al. A novel approach for protein-named entity recognition and protein-protein interaction extraction
AL-Khassawneh et al. Extractive Arabic text summarization-graph-based approach
Ciravegna et al. LODIE: Linked Open Data for Web-scale Information Extraction.
Zimmermann et al. Information extraction in the life sciences: perspectives for medicinal chemistry, pharmacology and toxicology
Mosa Data text mining based on Swarm Intelligence Techniques: Review of text summarization systems
Sharma et al. Comprehensive study of semantic annotation: Variant and praxis
Al-Baity et al. Computational linguistics based emotion detection and classification model on social networking data
Greene A generic framework for concept-based exploration of semi-Structured Software Engineering Data
Rasheed et al. Conversational chatbot system for student support in administrative exam information
Miksatko et al. What’s in a cluster? automatically detecting interesting interactions in student e-discussions
Caldas et al. Integration of construction documents in IFC project models
Mohemad et al. Ontological-based information extraction of construction tender documents
Opasjumruskit et al. Contron: Continuously trained ontology based on technical data sheets and wikidata
Ren et al. A method of domain dictionary construction for electric vehicles disassembly

Legal Events

Date Code Title Description
AS Assignment

Owner name: INGENUITY SYSTEMS, INC., CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:CHO, RAYMOND J.;CHEN, RICHARD O.;FELCIANO, RAMON M.;AND OTHERS;REEL/FRAME:023275/0811

Effective date: 20040624

AS Assignment

Owner name: INGENUITY SYSTEMS, INC., CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:CHO, RAYMOND J.;CHEN, RICHARD O.;FELCIANO, RAMON M.;AND OTHERS;REEL/FRAME:027912/0515

Effective date: 20040624

FEPP Fee payment procedure

Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

STCF Information on status: patent grant

Free format text: PATENTED CASE

FEPP Fee payment procedure

Free format text: PAT HOLDER NO LONGER CLAIMS SMALL ENTITY STATUS, ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: STOL); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

FEPP Fee payment procedure

Free format text: PAYER NUMBER DE-ASSIGNED (ORIGINAL EVENT CODE: RMPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

FPAY Fee payment

Year of fee payment: 4

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 8